rule-refactor by event4u-app

What it does—and where it fits

Use when the rule set is over the Augment budget, when a new rule would breach it, or when asked to audit / merge / prune rules — runs the audit pipeline and proposes a verdict per rule.

Best for

measureaugmentbudget --check fails (utilisation ≥ 0.95)
A new rule would push the budget over 0.95 — caught by the budget
User says "audit rules", "rule cleanup", "rules over budget",

Not for

Tasks that require unconfirmed production actions or broad system permissions.
Environments where the pinned source and install steps cannot be inspected.

Platform support, with evidence labels

Platform	Status	Evidence	What to check
Codex	Not declared	No explicit evidence	Portability before use
Claude Code	Not declared	No explicit evidence	Portability before use
Cursor	Not declared	No explicit evidence	Portability before use
Gemini CLI	Not declared	No explicit evidence	Portability before use

Open the compatibility checker

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource

npx skills add https://github.com/event4u-app/agent-config --skill "src/skills/rule-refactor"

Safe inspection promptEditorial

Inspect the Agent Skill "rule-refactor" from https://github.com/event4u-app/agent-config/blob/0adf49a8ae84b0ff6e2de8759eea43257e020eff/src/skills/rule-refactor/SKILL.md at commit 0adf49a8ae84b0ff6e2de8759eea43257e020eff. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

What the source asks the agent to do

Procedure

The audit infrastructure already exists — compose it:

merge → rewrite the surviving rule to cover both domains;delete → remove the file from .agent-src.uncondensed/rules/move-to-context → extract the body into

When to use

measureaugmentbudget --check fails (utilisation ≥ 0.95) A new rule would push the budget over 0.95 — caught by the budget gate in rule-writing User says "audit rules", "rule cleanup", "rules over budget", "prune rules", "merge rules", "rule system review" Periodic governance pas…

measureaugmentbudget --check fails (utilisation ≥ 0.95)A new rule would push the budget over 0.95 — caught by the budgetUser says "audit rules", "rule cleanup", "rules over budget",

Iron Law

Threshold-lift is forbidden. When the budget breaches, the content must shrink — not the gate. Loosening FAILTHRESHOLD in scripts/measureaugmentbudget.ts to make CI pass is an explicit anti-pattern. The only valid budget-growth move is an ADR that raises TOTALCAP.

1. Inspect the current budget state

Review the “1. Inspect the current budget state” section in the pinned source before continuing.

Review and apply the “1. Inspect the current budget state” source section.

2. Run the audit pipeline

The audit infrastructure already exists — compose it:

The audit infrastructure already exists — compose it:Then read agents/runtime/reports/auto-rules-audit.md end-to-end.

Signal	Value	Evidence type	Meaning
Quality score	91/100	Computed	Documentation, specificity, maintenance, and trust rules
Repository stars	7	Source	Repository attention, not individual Skill quality
Compatibility	0 platforms	Source	Declared in the catalog source record
Usage guide	automated source guide	Editorial	Generated or reviewed according to the visible evidence level

Signal

Value

Evidence type

Meaning

Quality score

91/100

Computed

Documentation, specificity, maintenance, and trust rules

Repository stars

Source

Repository attention, not individual Skill quality

Compatibility

0 platforms

Source

Declared in the catalog source record

Usage guide

automated source guide

Editorial

Generated or reviewed according to the visible evidence level

Provenance and original SKILL.md

Repository

event4u-app/agent-config

Skill path

src/skills/rule-refactor/SKILL.md

Commit

0adf49a8ae84b0ff6e2de8759eea43257e020eff

License

MIT

Collected

2026-07-28

Default branch

main

View the original SKILL.md

rule-refactor

When to use

measure_augment_budget --check fails (utilisation ≥ 0.95)
A new rule would push the budget over 0.95 — caught by the budget gate in rule-writing
User says "audit rules", "rule cleanup", "rules over budget", "prune rules", "merge rules", "rule system review"
Periodic governance pass after a batch of rule additions

Do NOT use this skill for:

Editing a single rule's content → rule-writing
Picking always vs auto for one new rule → rule-writing

Iron Law

Threshold-lift is forbidden. When the budget breaches, the content must shrink — not the gate. Loosening FAIL_THRESHOLD in scripts/measure_augment_budget.ts to make CI pass is an explicit anti-pattern. The only valid budget-growth move is an ADR that raises TOTAL_CAP.

Procedure

1. Inspect the current budget state

./scripts-run src/scripts/measure_augment_budget --json > /tmp/budget-before.json
./scripts-run src/scripts/measure_rule_budget --json > /tmp/rule-budget-before.json

2. Run the audit pipeline

The audit infrastructure already exists — compose it:

./scripts-run src/scripts/audit_auto_rules      # → agents/runtime/reports/auto-rules-audit.{json,md}
./scripts-run src/scripts/audit_overlap         # → appends overlap pairs to the MD
./scripts-run src/scripts/audit_likelihood      # → agents/runtime/reports/auto-rules-likelihood.json

Then read agents/runtime/reports/auto-rules-audit.md end-to-end.

3. Categorise every flagged rule

For each rule the audit surfaces (overlap pair, low-likelihood, oversized, or the new addition that triggered this skill), assign exactly one verdict:

Verdict	Test
keep	Iron-Law / always-on safety net, no overlap, fires often
merge	≥ 2 rules same domain, near-identical triggers, overlap ≥ 0.4
delete	Never fires (low-likelihood + no path/keyword hit in 30 days), or fully subsumed by a skill
move-to-context	Body is reference material (tables, mechanics, examples) — the obligation is short, the rest is lookup
promote-to-skill	Body has numbered steps / a workflow — not a constraint

4. Present the verdict table to the user

One Markdown table, one row per flagged rule, before any file change. User approves the list. No silent edits.

5. Apply approved changes

For each approved verdict:

merge → rewrite the surviving rule to cover both domains; delete the absorbed one; update any routes_to: references.
delete → remove the file from .agent-src.uncondensed/rules/ and the corresponding dist/agent-src/rules/ projection.
move-to-context → extract the body into .agent-src.uncondensed/contexts/<area>/<name>.md, replace the rule body with the obligation + a load_context: pointer.
promote-to-skill → create .agent-src.uncondensed/skills/<name>/SKILL.md, replace the rule with an auto-trigger stub that routes to it (or delete the rule entirely if the skill's own trigger suffices).

6. Re-validate

bash scripts/condense.sh --sync
./scripts-run src/scripts/condense --generate-tools
./scripts-run src/scripts/measure_augment_budget --check   # must exit 0
./scripts-run src/scripts/skill_linter --all               # 0 FAIL

Then run your package's full CI pipeline (see Taskfile.yml for the canonical sequence) before pushing.

7. Record the delta

Append a snapshot to agents/runtime/.augment-budget-history.jsonl:

./scripts-run src/scripts/measure_augment_budget --trend-append

Commit the cleanup as a separate chunk from any rule-add commits so the history shows "added X" + "cleaned up Y" as distinct steps.

Output format

Verdict table (approved by user) at the top of the cleanup PR description
Per-verdict commits (one per merge / delete / move / promote group)
Final measure_augment_budget --check output showing utilisation < 0.95
Trend snapshot recorded

Gotchas

Do NOT raise FAIL_THRESHOLD to dodge the audit
Do NOT delete a rule that has a routes_to: pointer without updating the pointer's source
Do NOT merge rules across tier boundaries (e.g. tier-1 always with a tier-3 stub) without surfacing the tier collapse to the user
Do NOT skip the trend-append — the history is what tells future agents how the cap was managed

Do NOT

Do NOT loosen the budget gate
Do NOT touch the cap (TOTAL_CAP) without an ADR
Do NOT apply changes before user approves the verdict table
Do NOT delete the rule-refactor audit reports — they're the artifact reviewers cite

Cloud Behavior

On cloud surfaces, the audit scripts are not reachable. The skill still applies — prose-only:

Inspect the rule list (frontmatter + descriptions) and propose the verdict table from reading alone.
Tell the user to run the audit scripts locally before applying.
Do not attempt to call any script.

rule-refactor

What it does—and where it fits

Best for

Not for

Platform support, with evidence labels

Inspect first. Install second.

What the source asks the agent to do

Procedure

When to use

Iron Law

1. Inspect the current budget state

2. Run the audit pipeline

Static risk signals and limitations

Writes files

Runs scripts

Why each signal appears

Provenance and original SKILL.md

rule-refactor

When to use

Iron Law

Procedure

1. Inspect the current budget state

2. Run the audit pipeline

3. Categorise every flagged rule

4. Present the verdict table to the user

5. Apply approved changes

6. Re-validate

7. Record the delta

Output format

Gotchas

Do NOT

Cloud Behavior